javbus, javlib use outline in airav

WebCrawler/airav.py

@@ -225,8 +225,8 @@ def main(number):
 if __name__ == '__main__':
     #print(main('ADN-188'))
 
-    print(search('ADN-188'))
+    print(main('ADN-188'))
-    print(search('012717_472'))
+    print(main('012717_472'))
-    print(search('080719-976'))
+    print(main('080719-976'))
-    print(search('姫川ゆうな'))
+    print(main('姫川ゆうな'))
 

WebCrawler/javbus.py

@@ -7,6 +7,7 @@ from bs4 import BeautifulSoup#need install
 import json
 from ADC_function import *
 from WebCrawler import fanza
+import airav
 
 def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
     soup = BeautifulSoup(htmlcode, 'lxml')
@@ -79,12 +80,13 @@ def getCID(htmlcode):
     string = html.xpath("//a[contains(@class,'sample-box')][1]/@href")[0].replace('https://pics.dmm.co.jp/digital/video/','')
     result = re.sub('/.*?.jpg','',string)
     return result
-def getOutline(htmlcode):  #获取演员
+def getOutline(number):  #获取演员
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
     try:
-        result = html.xpath("string(//div[contains(@class,'mg-b20 lh4')])").replace('\n','')
+        response = json.loads(airav.main(number))
+        result = response['outline']
         return result
-    except:
+    except Exception as e:
+        print(e)
         return ''
 def getSerise(htmlcode):   #获取系列 已修改
     html = etree.fromstring(htmlcode, etree.HTMLParser())
@@ -122,15 +124,11 @@ def main_uncensored(number):
     htmlcode = get_html('https://www.javbus.com/ja/' + number)
     if getTitle(htmlcode) == '':
         htmlcode = get_html('https://www.javbus.com/ja/' + number.replace('-','_'))
-    try:
-        dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
-    except:
-        dww_htmlcode = ''
     dic = {
         'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
         'studio': getStudio(htmlcode),
         'year': getYear(htmlcode),
-        'outline': getOutline(dww_htmlcode),
+        'outline': getOutline(number),
         'runtime': getRuntime(htmlcode),
         'director': getDirector(htmlcode),
         'actor': getActor(htmlcode),
@@ -157,15 +155,11 @@ def main(number):
                 htmlcode = get_html('https://www.fanbus.us/' + number)
             except:
                 htmlcode = get_html('https://www.javbus.com/' + number)
-            try:
-                dww_htmlcode = fanza.main_htmlcode(getCID(htmlcode))
-            except:
-                dww_htmlcode = ''
             dic = {
                 'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
                 'studio': getStudio(htmlcode),
                 'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
-                'outline': getOutline(dww_htmlcode),
+                'outline': getOutline(number),
                 'runtime': getRuntime(htmlcode),
                 'director': getDirector(htmlcode),
                 'actor': getActor(htmlcode),

WebCrawler/javlib.py

@@ -3,6 +3,7 @@ sys.path.append('../')
 import json
 import bs4
 import re
+import airav
 from bs4 import BeautifulSoup
 from lxml import html
 from http.cookies import SimpleCookie
@@ -42,7 +43,7 @@ def main(number: str):
             "title": get_title(lx, soup),
             "studio": get_table_el_single_anchor(soup, "video_maker"),
             "year": get_table_el_td(soup, "video_date")[:4],
-            "outline": "",
+            "outline": get_outline(number),
             "director": get_table_el_single_anchor(soup, "video_director"),
             "cover": get_cover(lx),
             "imagecut": 1,
@@ -77,7 +78,7 @@ def main(number: str):
             "title": get_title(lx, soup),
             "studio": get_table_el_single_anchor(soup, "video_maker"),
             "year": get_table_el_td(soup, "video_date")[:4],
-            "outline": "",
+            "outline": get_outline(number),
             "director": get_table_el_single_anchor(soup, "video_director"),
             "cover": get_cover(lx),
             "imagecut": 1,
@@ -102,6 +103,15 @@ def get_from_xpath(lx: html.HtmlElement, xpath: str) -> str:
     return lx.xpath(xpath)[0].strip()
 
 
+def get_outline(number):
+    try:
+        response = json.loads(airav.main(number))
+        result = response['outline']
+        return result
+    except:
+        return ''
+
+
 def get_table_el_single_anchor(soup: BeautifulSoup, tag_id: str) -> str:
     tag = soup.find(id=tag_id).find("a")
 
@@ -145,7 +155,7 @@ def get_cover(lx: html.HtmlComment) -> str:
 
 
 if __name__ == "__main__":
-    lists = ["DVMC-003", "GS-0167", "JKREZ-001", "KMHRS-010", "KNSD-023"]
+    lists = ["IPX-292", "STAR-438", "JKREZ-001", "KMHRS-010", "KNSD-023"]
     #lists = ["DVMC-003"]
     for num in lists:
         print(main(num))